Type Members

1.  final case class ChatCompletionRequestMessage(role: Role, content: String, name: Optional[String] = Optional.Absent) extends Product with Serializable

   ChatCompletionRequestMessage model

   ChatCompletionRequestMessage model

   role

   The role of the author of this message.

   content

   The contents of the message

   name

   The name of the user in a multi-user chat

2.  final case class ChatCompletionResponseMessage(role: Role, content: String) extends Product with Serializable

   ChatCompletionResponseMessage model

   ChatCompletionResponseMessage model

   role

   The role of the author of this message.

   content

   The contents of the message

3.  final case class CreateAnswerRequest(model: String, question: Question, examples: NonEmptyChunk[Chunk[ExamplesItemItem]], examplesContext: String, documents: Optional[Chunk[String]] = Optional.Absent, file: Optional[String] = Optional.Absent, searchModel: Optional[String] = Optional.Absent, maxRerank: Optional[Int] = Optional.Absent, temperature: Optional[Double] = Optional.Absent, logprobs: Optional[Logprobs] = Optional.Absent, maxTokens: Optional[Int] = Optional.Absent, stop: Optional[Stop] = Optional.Absent, n: Optional[CreateAnswerRequest.N] = Optional.Absent, logitBias: Optional[LogitBias] = Optional.Absent, returnMetadata: Optional[Boolean] = Optional.Absent, returnPrompt: Optional[Boolean] = Optional.Absent, expand: Optional[Chunk[ExpandItem]] = Optional.Absent, user: Optional[String] = Optional.Absent) extends Product with Serializable

   CreateAnswerRequest model

   CreateAnswerRequest model

   model

   ID of the model to use for completion. You can select one of ada, babbage, curie, or davinci.

   question

   Question to get answered.

   examples

   List of (question, answer) pairs that will help steer the model towards the tone and answer format you'd like. We recommend adding 2 to 3 examples.

   examplesContext

   A text snippet containing the contextual information used to generate the answers for the examples you provide.

   documents

   List of documents from which the answer for the input question should be derived. If this is an empty list, the question will be answered based on the question-answer examples. You should specify either documents or a file, but not both.

   file

   The ID of an uploaded file that contains documents to search over. See [upload file](/docs/api-reference/files/upload) for how to upload a file of the desired format and purpose. You should specify either documents or a file, but not both.

   searchModel

   ID of the model to use for [Search](/docs/api-reference/searches/create). You can select one of ada, babbage, curie, or davinci.

   maxRerank

   The maximum number of documents to be ranked by [Search](/docs/api-reference/searches/create) when using file. Setting it to a higher value leads to improved accuracy but with increased latency and cost.

   temperature

   What sampling temperature to use, between 0 and 2. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic.

   logprobs

   Include the log probabilities on the logprobs most likely tokens, as well the chosen tokens. For example, if logprobs is 5, the API will return a list of the 5 most likely tokens. The API will always return the logprob of the sampled token, so there may be up to logprobs+1 elements in the response. The maximum value for logprobs is 5. If you need more than this, please contact us through our [Help center](https://help.openai.com) and describe your use case. When logprobs is set, completion will be automatically added into expand to get the logprobs.

   maxTokens

   The maximum number of tokens allowed for the generated answer

   stop

   Up to 4 sequences where the API will stop generating further tokens. The returned text will not contain the stop sequence.

   n

   How many answers to generate for each question.

   logitBias

   Modify the likelihood of specified tokens appearing in the completion. Accepts a json object that maps tokens (specified by their token ID in the GPT tokenizer) to an associated bias value from -100 to 100. You can use this [tokenizer tool](/tokenizer?view=bpe) (which works for both GPT-2 and GPT-3) to convert text to token IDs. Mathematically, the bias is added to the logits generated by the model prior to sampling. The exact effect will vary per model, but values between -1 and 1 should decrease or increase likelihood of selection; values like -100 or 100 should result in a ban or exclusive selection of the relevant token. As an example, you can pass {"50256": -100} to prevent the <|endoftext|> token from being generated.

   returnMetadata

   A special boolean flag for showing metadata. If set to true, each document entry in the returned JSON will contain a "metadata" field. This flag only takes effect when file is set.

   returnPrompt

   If set to true, the returned JSON will include a "prompt" field containing the final prompt that was used to request a completion. This is mainly useful for debugging purposes.

   expand

   If an object name is in the list, we provide the full information of the object; otherwise, we only provide the object ID. Currently we support completion and file objects for expansion.

   user

   A unique identifier representing your end-user, which can help OpenAI to monitor and detect abuse. [Learn more](/docs/guides/safety-best-practices/end-user-ids).

4.  final case class CreateAnswerResponse(object: Optional[String] = Optional.Absent, model: Optional[String] = Optional.Absent, searchModel: Optional[String] = Optional.Absent, completion: Optional[String] = Optional.Absent, answers: Optional[Chunk[String]] = Optional.Absent, selectedDocuments: Optional[Chunk[SelectedDocumentsItem]] = Optional.Absent) extends Product with Serializable

   CreateAnswerResponse model

5.  final case class CreateChatCompletionRequest(model: String, messages: NonEmptyChunk[ChatCompletionRequestMessage], temperature: Optional[Temperature] = Optional.Absent, topP: Optional[TopP] = Optional.Absent, n: Optional[CreateChatCompletionRequest.N] = Optional.Absent, stream: Optional[Boolean] = Optional.Absent, stop: Optional[Stop] = Optional.Absent, maxTokens: Optional[Int] = Optional.Absent, presencePenalty: Optional[PresencePenalty] = Optional.Absent, frequencyPenalty: Optional[FrequencyPenalty] = Optional.Absent, logitBias: Optional[LogitBias] = Optional.Absent, user: Optional[String] = Optional.Absent) extends Product with Serializable

   CreateChatCompletionRequest model

   CreateChatCompletionRequest model

   model

   ID of the model to use. Currently, only gpt-3.5-turbo and gpt-3.5-turbo-0301 are supported.

   messages

   The messages to generate chat completions for, in the [chat format](/docs/guides/chat/introduction).

   temperature

   What sampling temperature to use, between 0 and 2. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic. We generally recommend altering this or top_p but not both.

   topP

   An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with top_p probability mass. So 0.1 means only the tokens comprising the top 10% probability mass are considered. We generally recommend altering this or temperature but not both.

   n

   How many chat completion choices to generate for each input message.

   stream

   If set, partial message deltas will be sent, like in ChatGPT. Tokens will be sent as data-only [server-sent events](https://developer.mozilla.org/en-US/docs/Web/API/Server-sent_events/Using_server-sent_events#Event_stream_format) as they become available, with the stream terminated by a data: [DONE] message.

   stop

   Up to 4 sequences where the API will stop generating further tokens.

   maxTokens

   The maximum number of tokens allowed for the generated answer. By default, the number of tokens the model can return will be (4096 - prompt tokens).

   presencePenalty

   Number between -2.0 and 2.0. Positive values penalize new tokens based on whether they appear in the text so far, increasing the model's likelihood to talk about new topics. [See more information about frequency and presence penalties.](/docs/api-reference/parameter-details)

   frequencyPenalty

   Number between -2.0 and 2.0. Positive values penalize new tokens based on their existing frequency in the text so far, decreasing the model's likelihood to repeat the same line verbatim. [See more information about frequency and presence penalties.](/docs/api-reference/parameter-details)

   logitBias

   Modify the likelihood of specified tokens appearing in the completion. Accepts a json object that maps tokens (specified by their token ID in the tokenizer) to an associated bias value from -100 to 100. Mathematically, the bias is added to the logits generated by the model prior to sampling. The exact effect will vary per model, but values between -1 and 1 should decrease or increase likelihood of selection; values like -100 or 100 should result in a ban or exclusive selection of the relevant token.

   user

   A unique identifier representing your end-user, which can help OpenAI to monitor and detect abuse. [Learn more](/docs/guides/safety-best-practices/end-user-ids).

6.  final case class CreateChatCompletionResponse(id: String, object: String, created: Int, model: String, choices: Chunk[ChoicesItem], usage: Optional[Usage] = Optional.Absent) extends Product with Serializable

   CreateChatCompletionResponse model

7.  final case class CreateClassificationRequest(model: String, query: Query, examples: Optional[Chunk[Chunk[ExamplesItemItem]]] = Optional.Absent, file: Optional[String] = Optional.Absent, labels: Optional[Chunk[String]] = Optional.Absent, searchModel: Optional[String] = Optional.Absent, temperature: Optional[CreateClassificationRequest.Temperature] = Optional.Absent, logprobs: Optional[Logprobs] = Optional.Absent, maxExamples: Optional[Int] = Optional.Absent, logitBias: Optional[LogitBias] = Optional.Absent, returnPrompt: Optional[Boolean] = Optional.Absent, returnMetadata: Optional[Boolean] = Optional.Absent, expand: Optional[Chunk[ExpandItem]] = Optional.Absent, user: Optional[String] = Optional.Absent) extends Product with Serializable

   CreateClassificationRequest model

   CreateClassificationRequest model

   model

   ID of the model to use. You can use the [List models](/docs/api-reference/models/list) API to see all of your available models, or see our [Model overview](/docs/models/overview) for descriptions of them.

   query

   Query to be classified.

   examples

   A list of examples with labels, in the following format: [ ["The movie is so interesting.", "Positive"], ["It is quite boring.", "Negative"], ...] All the label strings will be normalized to be capitalized. You should specify either examples or file, but not both.

   file

   The ID of the uploaded file that contains training examples. See [upload file](/docs/api-reference/files/upload) for how to upload a file of the desired format and purpose. You should specify either examples or file, but not both.

   labels

   The set of categories being classified. If not specified, candidate labels will be automatically collected from the examples you provide. All the label strings will be normalized to be capitalized.

   searchModel

   ID of the model to use for [Search](/docs/api-reference/searches/create). You can select one of ada, babbage, curie, or davinci.

   temperature

   What sampling temperature to use, between 0 and 2. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic.

   logprobs

   Include the log probabilities on the logprobs most likely tokens, as well the chosen tokens. For example, if logprobs is 5, the API will return a list of the 5 most likely tokens. The API will always return the logprob of the sampled token, so there may be up to logprobs+1 elements in the response. The maximum value for logprobs is 5. If you need more than this, please contact us through our [Help center](https://help.openai.com) and describe your use case. When logprobs is set, completion will be automatically added into expand to get the logprobs.

   maxExamples

   The maximum number of examples to be ranked by [Search](/docs/api-reference/searches/create) when using file. Setting it to a higher value leads to improved accuracy but with increased latency and cost.

   logitBias

   Modify the likelihood of specified tokens appearing in the completion. Accepts a json object that maps tokens (specified by their token ID in the GPT tokenizer) to an associated bias value from -100 to 100. You can use this [tokenizer tool](/tokenizer?view=bpe) (which works for both GPT-2 and GPT-3) to convert text to token IDs. Mathematically, the bias is added to the logits generated by the model prior to sampling. The exact effect will vary per model, but values between -1 and 1 should decrease or increase likelihood of selection; values like -100 or 100 should result in a ban or exclusive selection of the relevant token. As an example, you can pass {"50256": -100} to prevent the <|endoftext|> token from being generated.

   returnPrompt

   If set to true, the returned JSON will include a "prompt" field containing the final prompt that was used to request a completion. This is mainly useful for debugging purposes.

   returnMetadata

   A special boolean flag for showing metadata. If set to true, each document entry in the returned JSON will contain a "metadata" field. This flag only takes effect when file is set.

   expand

   If an object name is in the list, we provide the full information of the object; otherwise, we only provide the object ID. Currently we support completion and file objects for expansion.

   user

   A unique identifier representing your end-user, which can help OpenAI to monitor and detect abuse. [Learn more](/docs/guides/safety-best-practices/end-user-ids).

8.  final case class CreateClassificationResponse(object: Optional[String] = Optional.Absent, model: Optional[String] = Optional.Absent, searchModel: Optional[String] = Optional.Absent, completion: Optional[String] = Optional.Absent, label: Optional[String] = Optional.Absent, selectedExamples: Optional[Chunk[SelectedExamplesItem]] = Optional.Absent) extends Product with Serializable

   CreateClassificationResponse model

9.  final case class CreateCompletionRequest(model: String, prompt: Optional[Prompt] = Optional.Absent, suffix: Optional[String] = Optional.Absent, maxTokens: Optional[MaxTokens] = Optional.Absent, temperature: Optional[Temperature] = Optional.Absent, topP: Optional[TopP] = Optional.Absent, n: Optional[CreateCompletionRequest.N] = Optional.Absent, stream: Optional[Boolean] = Optional.Absent, logprobs: Optional[CreateCompletionRequest.Logprobs] = Optional.Absent, echo: Optional[Boolean] = Optional.Absent, stop: Optional[Stop] = Optional.Absent, presencePenalty: Optional[PresencePenalty] = Optional.Absent, frequencyPenalty: Optional[FrequencyPenalty] = Optional.Absent, bestOf: Optional[BestOf] = Optional.Absent, logitBias: Optional[LogitBias] = Optional.Absent, user: Optional[String] = Optional.Absent) extends Product with Serializable

   CreateCompletionRequest model

   CreateCompletionRequest model

   model

   ID of the model to use. You can use the [List models](/docs/api-reference/models/list) API to see all of your available models, or see our [Model overview](/docs/models/overview) for descriptions of them.

   prompt

   The prompt(s) to generate completions for, encoded as a string, array of strings, array of tokens, or array of token arrays. Note that <|endoftext|> is the document separator that the model sees during training, so if a prompt is not specified the model will generate as if from the beginning of a new document.

   suffix

   The suffix that comes after a completion of inserted text.

   maxTokens

   The maximum number of [tokens](/tokenizer) to generate in the completion. The token count of your prompt plus max_tokens cannot exceed the model's context length. Most models have a context length of 2048 tokens (except for the newest models, which support 4096).

   temperature

   What sampling temperature to use, between 0 and 2. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic. We generally recommend altering this or top_p but not both.

   topP

   An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with top_p probability mass. So 0.1 means only the tokens comprising the top 10% probability mass are considered. We generally recommend altering this or temperature but not both.

   n

   How many completions to generate for each prompt. **Note:** Because this parameter generates many completions, it can quickly consume your token quota. Use carefully and ensure that you have reasonable settings for max_tokens and stop.

   stream

   Whether to stream back partial progress. If set, tokens will be sent as data-only [server-sent events](https://developer.mozilla.org/en-US/docs/Web/API/Server-sent_events/Using_server-sent_events#Event_stream_format) as they become available, with the stream terminated by a data: [DONE] message.

   logprobs

   Include the log probabilities on the logprobs most likely tokens, as well the chosen tokens. For example, if logprobs is 5, the API will return a list of the 5 most likely tokens. The API will always return the logprob of the sampled token, so there may be up to logprobs+1 elements in the response. The maximum value for logprobs is 5. If you need more than this, please contact us through our [Help center](https://help.openai.com) and describe your use case.

   echo

   Echo back the prompt in addition to the completion

   stop

   Up to 4 sequences where the API will stop generating further tokens. The returned text will not contain the stop sequence.

   presencePenalty

   Number between -2.0 and 2.0. Positive values penalize new tokens based on whether they appear in the text so far, increasing the model's likelihood to talk about new topics. [See more information about frequency and presence penalties.](/docs/api-reference/parameter-details)

   frequencyPenalty

   Number between -2.0 and 2.0. Positive values penalize new tokens based on their existing frequency in the text so far, decreasing the model's likelihood to repeat the same line verbatim. [See more information about frequency and presence penalties.](/docs/api-reference/parameter-details)

   bestOf

   Generates best_of completions server-side and returns the "best" (the one with the highest log probability per token). Results cannot be streamed. When used with n, best_of controls the number of candidate completions and n specifies how many to return – best_of must be greater than n. **Note:** Because this parameter generates many completions, it can quickly consume your token quota. Use carefully and ensure that you have reasonable settings for max_tokens and stop.

   logitBias

   Modify the likelihood of specified tokens appearing in the completion. Accepts a json object that maps tokens (specified by their token ID in the GPT tokenizer) to an associated bias value from -100 to 100. You can use this [tokenizer tool](/tokenizer?view=bpe) (which works for both GPT-2 and GPT-3) to convert text to token IDs. Mathematically, the bias is added to the logits generated by the model prior to sampling. The exact effect will vary per model, but values between -1 and 1 should decrease or increase likelihood of selection; values like -100 or 100 should result in a ban or exclusive selection of the relevant token. As an example, you can pass {"50256": -100} to prevent the <|endoftext|> token from being generated.

   user

   A unique identifier representing your end-user, which can help OpenAI to monitor and detect abuse. [Learn more](/docs/guides/safety-best-practices/end-user-ids).

10.  final case class CreateCompletionResponse(id: String, object: String, created: Int, model: String, choices: Chunk[ChoicesItem], usage: Optional[Usage] = Optional.Absent) extends Product with Serializable

    CreateCompletionResponse model

11.  final case class CreateEditRequest(model: String, input: Optional[String] = Optional.Absent, instruction: String, n: Optional[CreateEditRequest.N] = Optional.Absent, temperature: Optional[Temperature] = Optional.Absent, topP: Optional[TopP] = Optional.Absent) extends Product with Serializable

    CreateEditRequest model

    CreateEditRequest model

    model

    ID of the model to use. You can use the text-davinci-edit-001 or code-davinci-edit-001 model with this endpoint.

    input

    The input text to use as a starting point for the edit.

    instruction

    The instruction that tells the model how to edit the prompt.

    n

    How many edits to generate for the input and instruction.

    temperature

    What sampling temperature to use, between 0 and 2. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic. We generally recommend altering this or top_p but not both.

    topP

    An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with top_p probability mass. So 0.1 means only the tokens comprising the top 10% probability mass are considered. We generally recommend altering this or temperature but not both.

12.  final case class CreateEditResponse(object: String, created: Int, choices: Chunk[ChoicesItem], usage: Usage) extends Product with Serializable

    CreateEditResponse model

13.  final case class CreateEmbeddingRequest(model: String, input: Input, user: Optional[String] = Optional.Absent) extends Product with Serializable

    CreateEmbeddingRequest model

    CreateEmbeddingRequest model

    model

    ID of the model to use. You can use the [List models](/docs/api-reference/models/list) API to see all of your available models, or see our [Model overview](/docs/models/overview) for descriptions of them.

    input

    Input text to get embeddings for, encoded as a string or array of tokens. To get embeddings for multiple inputs in a single request, pass an array of strings or array of token arrays. Each input must not exceed 8192 tokens in length.

    user

    A unique identifier representing your end-user, which can help OpenAI to monitor and detect abuse. [Learn more](/docs/guides/safety-best-practices/end-user-ids).

14.  final case class CreateEmbeddingResponse(object: String, model: String, data: Chunk[DataItem], usage: Usage) extends Product with Serializable

    CreateEmbeddingResponse model

15.  final case class CreateFileRequest(file: File, purpose: String) extends Product with Serializable

    CreateFileRequest model

    CreateFileRequest model

    file

    Name of the [JSON Lines](https://jsonlines.readthedocs.io/en/latest/) file to be uploaded. If the purpose is set to "fine-tune", each line is a JSON record with "prompt" and "completion" fields representing your [training examples](/docs/guides/fine-tuning/prepare-training-data).

    purpose

    The intended purpose of the uploaded documents. Use "fine-tune" for [Fine-tuning](/docs/api-reference/fine-tunes). This allows us to validate the format of the uploaded file.

16.  final case class CreateFineTuneRequest(trainingFile: String, validationFile: Optional[String] = Optional.Absent, model: Optional[String] = Optional.Absent, nEpochs: Optional[Int] = Optional.Absent, batchSize: Optional[Int] = Optional.Absent, learningRateMultiplier: Optional[Double] = Optional.Absent, promptLossWeight: Optional[Double] = Optional.Absent, computeClassificationMetrics: Optional[Boolean] = Optional.Absent, classificationNClasses: Optional[Int] = Optional.Absent, classificationPositiveClass: Optional[String] = Optional.Absent, classificationBetas: Optional[Chunk[Double]] = Optional.Absent, suffix: Optional[Suffix] = Optional.Absent) extends Product with Serializable

    CreateFineTuneRequest model

    CreateFineTuneRequest model

    trainingFile

    The ID of an uploaded file that contains training data. See [upload file](/docs/api-reference/files/upload) for how to upload a file. Your dataset must be formatted as a JSONL file, where each training example is a JSON object with the keys "prompt" and "completion". Additionally, you must upload your file with the purpose fine-tune. See the [fine-tuning guide](/docs/guides/fine-tuning/creating-training-data) for more details.

    validationFile

    The ID of an uploaded file that contains validation data. If you provide this file, the data is used to generate validation metrics periodically during fine-tuning. These metrics can be viewed in the [fine-tuning results file](/docs/guides/fine-tuning/analyzing-your-fine-tuned-model). Your train and validation data should be mutually exclusive. Your dataset must be formatted as a JSONL file, where each validation example is a JSON object with the keys "prompt" and "completion". Additionally, you must upload your file with the purpose fine-tune. See the [fine-tuning guide](/docs/guides/fine-tuning/creating-training-data) for more details.

    model

    The name of the base model to fine-tune. You can select one of "ada", "babbage", "curie", "davinci", or a fine-tuned model created after 2022-04-21. To learn more about these models, see the [Models](https://platform.openai.com/docs/models) documentation.

    nEpochs

    The number of epochs to train the model for. An epoch refers to one full cycle through the training dataset.

    batchSize

    The batch size to use for training. The batch size is the number of training examples used to train a single forward and backward pass. By default, the batch size will be dynamically configured to be ~0.2% of the number of examples in the training set, capped at 256 - in general, we've found that larger batch sizes tend to work better for larger datasets.

    learningRateMultiplier

    The learning rate multiplier to use for training. The fine-tuning learning rate is the original learning rate used for pretraining multiplied by this value. By default, the learning rate multiplier is the 0.05, 0.1, or 0.2 depending on final batch_size (larger learning rates tend to perform better with larger batch sizes). We recommend experimenting with values in the range 0.02 to 0.2 to see what produces the best results.

    promptLossWeight

    The weight to use for loss on the prompt tokens. This controls how much the model tries to learn to generate the prompt (as compared to the completion which always has a weight of 1.0), and can add a stabilizing effect to training when completions are short. If prompts are extremely long (relative to completions), it may make sense to reduce this weight so as to avoid over-prioritizing learning the prompt.

    computeClassificationMetrics

    If set, we calculate classification-specific metrics such as accuracy and F-1 score using the validation set at the end of every epoch. These metrics can be viewed in the [results file](/docs/guides/fine-tuning/analyzing-your-fine-tuned-model). In order to compute classification metrics, you must provide a validation_file. Additionally, you must specify classification_n_classes for multiclass classification or classification_positive_class for binary classification.

    classificationNClasses

    The number of classes in a classification task. This parameter is required for multiclass classification.

    classificationPositiveClass

    The positive class in binary classification. This parameter is needed to generate precision, recall, and F1 metrics when doing binary classification.

    classificationBetas

    If this is provided, we calculate F-beta scores at the specified beta values. The F-beta score is a generalization of F-1 score. This is only used for binary classification. With a beta of 1 (i.e. the F-1 score), precision and recall are given the same weight. A larger beta score puts more weight on recall and less on precision. A smaller beta score puts more weight on precision and less on recall.

    suffix

    A string of up to 40 characters that will be added to your fine-tuned model name. For example, a suffix of "custom-model-name" would produce a model name like ada:ft-your-org:custom-model-name-2022-02-15-04-21-04.

17.  final case class CreateImageEditRequest(image: File, mask: Optional[File] = Optional.Absent, prompt: String, n: Optional[N] = Optional.Absent, size: Optional[Size] = Optional.Absent, responseFormat: Optional[ResponseFormat] = Optional.Absent, user: Optional[String] = Optional.Absent) extends Product with Serializable

    CreateImageEditRequest model

    CreateImageEditRequest model

    image

    The image to edit. Must be a valid PNG file, less than 4MB, and square. If mask is not provided, image must have transparency, which will be used as the mask.

    mask

    An additional image whose fully transparent areas (e.g. where alpha is zero) indicate where image should be edited. Must be a valid PNG file, less than 4MB, and have the same dimensions as image.

    prompt

    A text description of the desired image(s). The maximum length is 1000 characters.

    n

    The number of images to generate. Must be between 1 and 10.

    size

    The size of the generated images. Must be one of 256x256, 512x512, or 1024x1024.

    responseFormat

    The format in which the generated images are returned. Must be one of url or b64_json.

    user

    A unique identifier representing your end-user, which can help OpenAI to monitor and detect abuse. [Learn more](/docs/guides/safety-best-practices/end-user-ids).

18.  final case class CreateImageRequest(prompt: String, n: Optional[N] = Optional.Absent, size: Optional[Size] = Optional.Absent, responseFormat: Optional[ResponseFormat] = Optional.Absent, user: Optional[String] = Optional.Absent) extends Product with Serializable

    CreateImageRequest model

    CreateImageRequest model

    prompt

    A text description of the desired image(s). The maximum length is 1000 characters.

    n

    The number of images to generate. Must be between 1 and 10.

    size

    The size of the generated images. Must be one of 256x256, 512x512, or 1024x1024.

    responseFormat

    The format in which the generated images are returned. Must be one of url or b64_json.

    user

    A unique identifier representing your end-user, which can help OpenAI to monitor and detect abuse. [Learn more](/docs/guides/safety-best-practices/end-user-ids).

19.  final case class CreateImageVariationRequest(image: File, n: Optional[N] = Optional.Absent, size: Optional[Size] = Optional.Absent, responseFormat: Optional[ResponseFormat] = Optional.Absent, user: Optional[String] = Optional.Absent) extends Product with Serializable

    CreateImageVariationRequest model

    CreateImageVariationRequest model

    image

    The image to use as the basis for the variation(s). Must be a valid PNG file, less than 4MB, and square.

    n

    The number of images to generate. Must be between 1 and 10.

    size

    The size of the generated images. Must be one of 256x256, 512x512, or 1024x1024.

    responseFormat

    The format in which the generated images are returned. Must be one of url or b64_json.

    user

    A unique identifier representing your end-user, which can help OpenAI to monitor and detect abuse. [Learn more](/docs/guides/safety-best-practices/end-user-ids).

20.  final case class CreateModerationRequest(input: Input, model: Optional[String] = Optional.Absent) extends Product with Serializable

    CreateModerationRequest model

    CreateModerationRequest model

    input

    The input text to classify

    model

    Two content moderations models are available: text-moderation-stable and text-moderation-latest. The default is text-moderation-latest which will be automatically upgraded over time. This ensures you are always using our most accurate model. If you use text-moderation-stable, we will provide advanced notice before updating the model. Accuracy of text-moderation-stable may be slightly lower than for text-moderation-latest.

21.  final case class CreateModerationResponse(id: String, model: String, results: Chunk[ResultsItem]) extends Product with Serializable

    CreateModerationResponse model

22.  final case class CreateSearchRequest(query: Query, documents: Optional[NonEmptyChunk[String]] = Optional.Absent, file: Optional[String] = Optional.Absent, maxRerank: Optional[MaxRerank] = Optional.Absent, returnMetadata: Optional[Boolean] = Optional.Absent, user: Optional[String] = Optional.Absent) extends Product with Serializable

    CreateSearchRequest model

    CreateSearchRequest model

    query

    Query to search against the documents.

    documents

    Up to 200 documents to search over, provided as a list of strings. The maximum document length (in tokens) is 2034 minus the number of tokens in the query. You should specify either documents or a file, but not both.

    file

    The ID of an uploaded file that contains documents to search over. You should specify either documents or a file, but not both.

    maxRerank

    The maximum number of documents to be re-ranked and returned by search. This flag only takes effect when file is set.

    returnMetadata

    A special boolean flag for showing metadata. If set to true, each document entry in the returned JSON will contain a "metadata" field. This flag only takes effect when file is set.

    user

    A unique identifier representing your end-user, which can help OpenAI to monitor and detect abuse. [Learn more](/docs/guides/safety-best-practices/end-user-ids).

23.  final case class CreateSearchResponse(object: Optional[String] = Optional.Absent, model: Optional[String] = Optional.Absent, data: Optional[Chunk[DataItem]] = Optional.Absent) extends Product with Serializable

    CreateSearchResponse model

24.  final case class CreateTranscriptionRequest(file: File, model: String, prompt: Optional[String] = Optional.Absent, responseFormat: Optional[String] = Optional.Absent, temperature: Optional[Double] = Optional.Absent, language: Optional[String] = Optional.Absent) extends Product with Serializable

    CreateTranscriptionRequest model

    CreateTranscriptionRequest model

    file

    The audio file to transcribe, in one of these formats: mp3, mp4, mpeg, mpga, m4a, wav, or webm.

    model

    ID of the model to use. Only whisper-1 is currently available.

    prompt

    An optional text to guide the model's style or continue a previous audio segment. The [prompt](/docs/guides/speech-to-text/prompting) should match the audio language.

    responseFormat

    The format of the transcript output, in one of these options: json, text, srt, verbose_json, or vtt.

    temperature

    The sampling temperature, between 0 and 1. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic. If set to 0, the model will use [log probability](https://en.wikipedia.org/wiki/Log_probability) to automatically increase the temperature until certain thresholds are hit.

    language

    The language of the input audio. Supplying the input language in [ISO-639-1](https://en.wikipedia.org/wiki/List_of_ISO_639-1_codes) format will improve accuracy and latency.

25.  final case class CreateTranscriptionResponse(text: String) extends Product with Serializable

    CreateTranscriptionResponse model

26.  final case class CreateTranslationRequest(file: File, model: String, prompt: Optional[String] = Optional.Absent, responseFormat: Optional[String] = Optional.Absent, temperature: Optional[Double] = Optional.Absent) extends Product with Serializable

    CreateTranslationRequest model

    CreateTranslationRequest model

    file

    The audio file to translate, in one of these formats: mp3, mp4, mpeg, mpga, m4a, wav, or webm.

    model

    ID of the model to use. Only whisper-1 is currently available.

    prompt

    An optional text to guide the model's style or continue a previous audio segment. The [prompt](/docs/guides/speech-to-text/prompting) should be in English.

    responseFormat

    The format of the transcript output, in one of these options: json, text, srt, verbose_json, or vtt.

    temperature

    The sampling temperature, between 0 and 1. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic. If set to 0, the model will use [log probability](https://en.wikipedia.org/wiki/Log_probability) to automatically increase the temperature until certain thresholds are hit.

27.  final case class CreateTranslationResponse(text: String) extends Product with Serializable

    CreateTranslationResponse model

28.  final case class DeleteFileResponse(id: String, object: String, deleted: Boolean) extends Product with Serializable

    DeleteFileResponse model

29.  final case class DeleteModelResponse(id: String, object: String, deleted: Boolean) extends Product with Serializable

    DeleteModelResponse model

30.  final case class Engine(id: String, object: String, created: Optional[Int], ready: Boolean) extends Product with Serializable

    Engine model

31.  final case class Error(message: String, type: String, param: Option[String], code: Option[String]) extends Product with Serializable
32.  final case class ErrorResponse(error: Error) extends Product with Serializable
33.  type ExamplesItemItem = model.ExamplesItemItem.Type

    examples_item_item model

34.  final case class File(data: Chunk[Byte], fileName: String) extends Product with Serializable
35.  final case class FineTune(id: String, object: String, createdAt: Int, updatedAt: Int, model: String, fineTunedModel: Optional[String], organizationId: String, status: String, hyperparams: Hyperparams, trainingFiles: Chunk[OpenAIFile], validationFiles: Chunk[OpenAIFile], resultFiles: Chunk[OpenAIFile], events: Optional[Chunk[FineTuneEvent]] = Optional.Absent) extends Product with Serializable

    FineTune model

36.  final case class FineTuneEvent(object: String, createdAt: Int, level: String, message: String) extends Product with Serializable

    FineTuneEvent model

37.  type FrequencyPenalty = model.FrequencyPenalty.Type

    frequency_penalty model

    frequency_penalty model

    Number between -2.0 and 2.0. Positive values penalize new tokens based on their existing frequency in the text so far, decreasing the model's likelihood to repeat the same line verbatim.

    [See more information about frequency and presence penalties.](/docs/api-reference/parameter-details)

38.  final case class ImagesResponse(created: Int, data: Chunk[DataItem]) extends Product with Serializable

    ImagesResponse model

39.  final case class ListEnginesResponse(object: String, data: Chunk[Engine]) extends Product with Serializable

    ListEnginesResponse model

40.  final case class ListFilesResponse(object: String, data: Chunk[OpenAIFile]) extends Product with Serializable

    ListFilesResponse model

41.  final case class ListFineTuneEventsResponse(object: String, data: Chunk[FineTuneEvent]) extends Product with Serializable

    ListFineTuneEventsResponse model

42.  final case class ListFineTunesResponse(object: String, data: Chunk[FineTune]) extends Product with Serializable

    ListFineTunesResponse model

43.  final case class ListModelsResponse(object: String, data: Chunk[Model]) extends Product with Serializable

    ListModelsResponse model

44.  type Logprobs = model.Logprobs.Type

    logprobs model

    logprobs model

    Include the log probabilities on the logprobs most likely tokens, as well the chosen tokens. For example, if logprobs is 5, the API will return a list of the 5 most likely tokens. The API will always return the logprob of the sampled token, so there may be up to logprobs+1 elements in the response.

    The maximum value for logprobs is 5. If you need more than this, please contact us through our [Help center](https://help.openai.com) and describe your use case.

    When logprobs is set, completion will be automatically added into expand to get the logprobs.

45.  final case class Model(id: String, object: String, created: Int, ownedBy: String) extends Product with Serializable

    Model model

46.  type N = model.N.Type

    n model

    n model

    The number of images to generate. Must be between 1 and 10.

47.  sealed trait OpenAIFailure extends AnyRef
48.  final case class OpenAIFile(id: String, object: String, bytes: Int, createdAt: Int, filename: String, purpose: String, status: Optional[String] = Optional.Absent, statusDetails: Optional[StatusDetails] = Optional.Absent) extends Product with Serializable

    OpenAIFile model

49.  type PresencePenalty = model.PresencePenalty.Type

    presence_penalty model

    presence_penalty model

    Number between -2.0 and 2.0. Positive values penalize new tokens based on whether they appear in the text so far, increasing the model's likelihood to talk about new topics.

    [See more information about frequency and presence penalties.](/docs/api-reference/parameter-details)

50.  sealed trait ResponseFormat extends AnyRef

    response_format model

    response_format model

    The format in which the generated images are returned. Must be one of url or b64_json.

51.  sealed trait Role extends AnyRef

    role model

    role model

    The role of the author of this message.

52.  sealed trait Size extends AnyRef

    size model

    size model

    The size of the generated images. Must be one of 256x256, 512x512, or 1024x1024.

53.  type Temperature = model.Temperature.Type

    temperature model

    temperature model

    What sampling temperature to use, between 0 and 2. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic.

    We generally recommend altering this or top_p but not both.

54.  type TopP = model.TopP.Type

    top_p model

    top_p model

    An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with top_p probability mass. So 0.1 means only the tokens comprising the top 10% probability mass are considered.

    We generally recommend altering this or temperature but not both.